Journal of the Korea Convergence Society (한국융합학회논문지)

Korea Convergence Society (한국융합학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Curation Factors through Reverse Engineering Design of YouTube Algorithm - Focusing on Gender Keyword Search

유튜브 알고리즘의 역공학설계를 통한 큐레이션 요인 연구 - 성별 키워드 검색을 중심으로

  • Received : 2021.12.03
  • Accepted : 2022.03.20
  • Published : 2022.03.28
Download PDF
⟨ Previous Next ⟩

Abstract

Despite the fact that Internet users around the world watch YouTube every day, very few users accurately recognize the recommendation algorithm for search results, and Google and YouTube are not disclosing it. Researchers tried to explore the undisclosed algorithm of YouTube in a reverse engineering design method, find key factors, and check the logical structure in which media platform operators recommend keyword search results and arrange them on the screen. Therefore, researchers studied the basic content priority factors through several months of discussion and data collection, and tried to reverse engineer the influencing factors based on the recommendation results according to male and female gender among the collected keyword search results. Although researchers' design only analyzed some of the almost infinite level of data uploaded and viewed for more than hundreds of hours every hour, these exploratory attempts will study media platform algorithms in the future, understand the intentions of operators, and protect users. thought it could be done.

전 세계의 인터넷 사용자들이 매일 유튜브를 시청하지만, 검색결과에 대한 추천 알고리즘을 정확히 인지하는 이용자는 극히 드물며, 구글과 유튜브는 이를 공개하지 않고 있다. 연구자들은 공개되어 있지 않은 유튜브의 알고리즘을 역공학설계 방식으로 탐색하고, 핵심적 요인을 찾아 미디어 플랫폼 사업자들이 어떤 논리적 구조로 키워드 검색결과를 추천하고, 화면에 배열하는지 확인하고자 하였다. 따라서 연구자들은 수개월에 걸친 논의와 데이터의 수집을 통해 기초적인 콘텐츠 우선순위 요인을 연구하였으며 수집된 키워드 검색 결과 중에 남, 여 성별에 따른 추천결과를 토대로 영향 요인을 역설계하고자 하였다. 비록 연구자들의 설계는 매시간 수백시간 이상 업로드되고 시청되는 거의 무한한 수준의 데이터 중에서 일부를 분석한 것에 그치지 않지만, 이러한 탐색적 시도가 향후 미디어 플랫폼 알고리즘을 연구하고, 사업자들의 의도를 파악하며, 사용자를 보호할 수 있을 것으로 보았다.

Keywords

Acknowledgement

This research was supported by Basic Science Research Program through the National Research Foundation of Korea(NRF) funded by the Ministry of Education (NRF-2021-R1I1A3054903).

References

  1. J. Cheney Lippold. (2011). A New Algorithmic Identity : Soft Bio Politics and the Modulation of Control, Theory, Culture & Society, 28(6), 164-181. https://doi.org/10.1177/0263276411424420
  2. S. E. Park, Y. Y. Hwang & J. S. Yoon. (2017). Performance Evaluation of Recommendation Results through Optimization on Content Recommendation Algorithm Applying Personalization in Scientific Information Service Platform, Journal of the Korea Contents Association, 17(11), 183-191. https://doi.org/10.5392/JKCA.2017.17.11.183
  3. M. Kearns & A. Roth. (2020). Ethical Algorithm Design, ACM SIGecom Exchanges, 18,(1), 31-36. https://doi.org/10.1145/3440959.3440966
  4. R. Kowalski. (1979). Algorithm=logic+control, Communications of the ACM, 22(7), 424-436. https://doi.org/10.1145/359131.359136
  5. A. Rouvroy(2013). The End(s) of Critique : Data-Behaviourism vs. Due-Process, Privacy, Due Process and the Computational Turn, Routledge.
  6. S. Arnold. (2016). Abstract Title : Netflix and the Myth of Choice/Participation/Autonomy, Bloomsbury.
  7. H. Fry. (2018). Hello World: How to be Human in the Age of the Machine, Random House.
  8. S. J. Bae (2020). Trend Analysis of Movie Content Curation and Metadata Standards Research : Focus on the Art Management Perspective, Journal of the Korea Convergence Society, 11(6), 163-171. https://doi.org/10.15207/JKCS.2020.11.6.163
  9. R. Kitchin. (2014). Thinking Critically about and Researching Algorithms. Programmable City Working Paper 5.
  10. S. W. Oh. (2016). An Exploratory Inquiry into the Convergence of Journalism and Algorithm, Journal of Cyber communication academic Society, 33(3), 51-101.
  11. N. Katherine Hayles. (2010). How we read: Close, Hyper, Machine. ADE bulletin, 150(18), 62-79. https://doi.org/10.1632/ade.150.62
  12. A. Halavais. (2008). The Search Engine Society. Cambridge: Polity.
  13. S. Levy. (2010). How Google's algorithm rules the web. Wired Magazine, 18(3).
  14. S. H. Lee. (2020). Return of Barbarism, YouTube Reality and Prospect, Yerinwon.
  15. HankyungIT. (2021.4.18.). Naver lost its No. 1 spot to Google or its decisive shot changed its fate. https://www.hankyung.com/it/article/202104187645i
  16. S. W. Oh & H. Y. Song. (2019). YouTube Recommendation Algorithm and Journalism, Korea Press Foundation.
  17. Y. S. Yun & H. U. Lee. (2016). Personal Broadcasting Platform Technology : Focusing on Afreeca TV and YouTube, Information and Communications Magazine, 33(4), 56-63.
  18. The Science Times (2021.5.25.). How to get the algorithm's choice? https://www.sciencetimes.co.kr/news/save
  19. N. D. Kim, J. Y. Lee, D. G. Kwak & H. J. Kim. (2018). A Study on the Reasonable Improvement of Regulation of Local Civil Broadcasting Organization, Korea Information Society Development Institute.
  20. G. Enli & T. Sybertsen. (2016). The end of television-again! TV is still influenced by cultural factors in the age of digital intermediaries. Media and Communication, 4(3), 142-153. https://doi.org/10.17645/mac.v4i3.547
  21. H. E. Lee. (2019). Exploring YouTube as a form of Technology and culture : Concepts of 'flow' and algorithm in digital culture network, Media & Society, 27(2), 5-42.
  22. Reuters Institute. (2021). Digital News Report 21, https://reutersinstitute.politics.ox.ac.uk/digitalnews-report/2021/south-korea.
  23. HS. Becker. (1982). Art Worlds, Beckeley : University of california Press.
  24. S. W. Oh. (2019). Understanding YouTube's media orientation as an algorithm, Kwanhun Journal, 61(1), 11-17.
  25. T. Gillespie. (2010). The politics of 'platforms'. New media & society, 12(3), 347-364. https://doi.org/10.1177/1461444809342738
  26. P. Vonderau. (2016). The video bubble: Multichannel networks and the transformation of YouTube. Convergence, 22(4), 361-375. https://doi.org/10.1177/1354856516641882
  27. K. Roose. (2019). YouTube's Product Chief on Online Radicalization and Algorithmic Rabbit Holes. The New York Times.
  28. H. S. Kim. (2020). Analysis of Popular YouTube Video Content using Data Mining, Journal of Digital Contents Society, 21(4), 673-681. https://doi.org/10.9728/dcs.2020.21.4.673
  29. S. H. Sohn. (2005). Competition and Substitution of Digital Media : Usage Patterns of News, Sports, and Adult Contents, Journal of Cybercommunication Academic Society, (16), 273-308.
  30. J. B. Choi & M. S. Lee. (2017). News Contents Consumption Analysis of News Consumers in the Era of New Media, Journal of the Korea Contents Association, 17(2), 207-218. https://doi.org/10.5392/JKCA.2017.17.02.207
  31. Y. J. Yang & H. K. Chun. (2021). Analysis of YouTube Contents for Young Children and Evaluation of Their Suitability, Journal of Children's Media & Education, 20(3), 27-57.
  32. U. A, Kwon & S. C, Kim. (2013). A Study on the Changes of the Sex Appeals in the Korean TV commercials : Content Analysis of TV ads since 1996, Broadcasting & Communication, 14(2), 207-252.
  33. J. S. Kim & S. M. Youn. (2019). How does Hate Speech become a Business in Internet Personal Broadcasting? : Focusing on a Talk/Camcorder Genre Broadcasting on YouTube and Afreeca TV, Korean Journal of Broadcasting and Telecommunication Studies, 33(3), 45-79. https://doi.org/10.22876/KAB.2019.33.3.002
  34. J. E. Song & W. H. Jang. (2013). Developing the Korean Wave through Encouraging the Participation of YouTube users : The Case Study of the Korean Wave Youth Fans in Hong kong, Journal of The Korea Contents Association, 13(4), 155-169. https://doi.org/10.5392/JKCA.2013.13.04.155
  35. J. Y. Lee. (2015). Study on Hate Speech from an International Human Rights Law Perspective with Focus on Incitement to Hartred, The Korean Journal of International law, 60(3), 195-227.
  36. Q. Xu. (2013). "Social recommendation, source credibility, and recency: Effects of news cues in a social bookmarking website", Journalism & Mass Communication Quarterly, 90(4), 757-775. https://doi.org/10.1177/1077699013503158
  37. The Random House Dictionary. (1987). p1744
  38. W. R. Davie & J. S. Lee. (1995). Sex, violence, and consonance/differentiation: An analysis of local TV news values. Journalism & Mass Communication Quarterly, 72(1), 128-138. https://doi.org/10.1177/107769909507200110
  39. 1969 Mott, F. L. (1941). American journalism : A history of newspapers in the United States through 250 years, 1690-1940. New York : Macmillan.
  40. J. W. Lee. (2021). How has the Entertainment News production Practices Changed Since the Portal site's Introduction of Al News Curation? : An Exploratory Study, Journal of Broadcasting and Telecommunication Research, 113, 93-121.
  41. Y. J. Chung & Y. J. Choi. (2017). Repeated Viewing of Short Edited Video Clip of Social Events : The Effect of Transportation, Identification, Vicarious Pleasure on Loop watching, Journal of Media Economics & Culture, 15(3), 86-134. https://doi.org/10.21328/JMEC.2017.8.15.3.86
  42. The Korea Creative Content Agency (KOCCA)(2015). Current status of web content of broadcast video and plan for activation, 15-36.